English
Related papers

Related papers: Black Box Explanation by Learning Image Exemplars …

200 papers

Model agnostic feature attribution algorithms (such as SHAP and LIME) are ubiquitous techniques for explaining the decisions of complex classification models, such as deep neural networks. However, since complex classification models…

Machine Learning · Computer Science 2022-11-29 Ron Bitton , Alon Malach , Amiel Meiseles , Satoru Momiyama , Toshinori Araki , Jun Furukawa , Yuval Elovici , Asaf Shabtai

In this paper we propose a method to obtain global explanations for trained black-box classifiers by sampling their decision function to learn alternative interpretable models. The envisaged approach provides a unified solution to…

Machine Learning · Computer Science 2018-11-26 Irene Unceta , Jordi Nin , Oriol Pujol

Counterfactual Explanations are becoming a de-facto standard in post-hoc interpretable machine learning. For a given classifier and an instance classified in an undesired class, its counterfactual explanation corresponds to small…

Machine Learning · Computer Science 2024-01-17 Veronica Piccialli , Dolores Romero Morales , Cecilia Salvatore

Deep neural networks are widely used for classification. These deep models often suffer from a lack of interpretability -- they are particularly difficult to understand because of their non-linear nature. As a result, neural networks are…

Artificial Intelligence · Computer Science 2017-11-22 Oscar Li , Hao Liu , Chaofan Chen , Cynthia Rudin

We present a mechanism for detecting adversarial examples based on data representations taken from the hidden layers of the target network. For this purpose, we train individual autoencoders at intermediate layers of the target network.…

Machine Learning · Computer Science 2020-06-18 Bartosz Wójcik , Paweł Morawiecki , Marek Śmieja , Tomasz Krzyżek , Przemysław Spurek , Jacek Tabor

Given an image, generating its natural language description (i.e., caption) is a well studied problem. Approaches proposed to address this problem usually rely on image features that are difficult to interpret. Particularly, these image…

Computer Vision and Pattern Recognition · Computer Science 2020-07-24 Aditya Mogadala , Xiaoyu Shen , Dietrich Klakow

We study utilizing auxiliary information in training data to improve the trustworthiness of machine learning models. Specifically, in the context of image classification, we propose to optimize a training objective that incorporates…

Computer Vision and Pattern Recognition · Computer Science 2021-08-24 Dharma KC , Chicheng Zhang

The success of deep neural nets heavily relies on their ability to encode complex relations between their input and their output. While this property serves to fit the training data well, it also obscures the mechanism that drives…

Machine Learning · Computer Science 2021-12-10 Itai Gat , Guy Lorberbom , Idan Schwartz , Tamir Hazan

Autoencoders are a common building block of Deep Learning architectures, where they are mainly used for representation learning. They have also been successfully used in Collaborative Filtering (CF) recommender systems to predict missing…

Information Retrieval · Computer Science 2020-01-14 Pegah Sagheb Haghighi , Olurotimi Seton , Olfa Nasraoui

In this work, we study different approaches to self-supervised pretraining of object detection models. We first design a general framework to learn a spatially consistent dense representation from an image, by randomly sampling and…

Computer Vision and Pattern Recognition · Computer Science 2022-08-12 Trung Dang , Simon Kornblith , Huy Thong Nguyen , Peter Chin , Maryam Khademi

The increasing impact of black box models, and particularly of unsupervised ones, comes with an increasing interest in tools to understand and interpret them. In this paper, we consider in particular how to characterise visual groupings…

Computer Vision and Pattern Recognition · Computer Science 2020-10-29 Iro Laina , Ruth C. Fong , Andrea Vedaldi

Contrastive explanations clarify why an event occurred in contrast to another. They are more inherently intuitive to humans to both produce and comprehend. We propose a methodology to produce contrastive explanations for classification…

Computation and Language · Computer Science 2021-09-15 Alon Jacovi , Swabha Swayamdipta , Shauli Ravfogel , Yanai Elazar , Yejin Choi , Yoav Goldberg

Deep learning models are vulnerable to adversarial examples, which can fool a target classifier by imposing imperceptible perturbations onto natural examples. In this work, we consider the practical and challenging decision-based black-box…

Machine Learning · Computer Science 2021-05-11 Qi-An Fu , Yinpeng Dong , Hang Su , Jun Zhu

We consider the problem of explaining the predictions of an arbitrary blackbox model $f$: given query access to $f$ and an instance $x$, output a small set of $x$'s features that in conjunction essentially determines $f(x)$. We design an…

Machine Learning · Computer Science 2021-11-03 Guy Blanc , Jane Lange , Li-Yang Tan

Interpretability is highly desired for deep neural network-based classifiers, especially when addressing high-stake decisions in medical imaging. Commonly used post-hoc interpretability methods have the limitation that they can produce…

Image and Video Processing · Electrical Eng. & Systems 2024-01-04 Sourya Sengupta , Mark A. Anastasio

We present an interpretable companion model for any pre-trained black-box classifiers. The idea is that for any input, a user can decide to either receive a prediction from the black-box model, with high accuracy but no explanations, or…

Machine Learning · Statistics 2020-02-12 Danqing Pan , Tong Wang , Satoshi Hara

In the last years many accurate decision support systems have been constructed as black boxes, that is as systems that hide their internal logic to the user. This lack of explanation constitutes both a practical and an ethical issue. The…

Computers and Society · Computer Science 2018-06-22 Riccardo Guidotti , Anna Monreale , Salvatore Ruggieri , Franco Turini , Dino Pedreschi , Fosca Giannotti

Explaining the behavior of a black box machine learning model at the instance level is useful for building trust. However, it is also important to understand how the model behaves globally. Such an understanding provides insight into both…

Artificial Intelligence · Computer Science 2018-06-18 Nikaash Puri , Piyush Gupta , Pratiksha Agarwal , Sukriti Verma , Balaji Krishnamurthy

Interpretability has become incredibly important as machine learning is increasingly used to inform consequential decisions. We propose to construct global explanations of complex, blackbox models in the form of a decision tree…

Machine Learning · Computer Science 2019-01-28 Osbert Bastani , Carolyn Kim , Hamsa Bastani

We present a technique for translating a black-box machine-learned classifier operating on a high-dimensional input space into a small set of human-interpretable observables that can be combined to make the same classification decisions. We…

High Energy Physics - Phenomenology · Physics 2021-04-21 Taylor Faucett , Jesse Thaler , Daniel Whiteson